Upload TFT5ForConditionalGeneration

README.md

@@ -4,19 +4,19 @@ base_model: t5-base
 tags:
 - generated_from_keras_callback
 model-index:
-- name: demo
+- name: text-summarization-t5-base
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# demo
+# text-summarization-t5-base
 
 This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.1621
-- Validation Loss: 0.8490
+- Train Loss: 1.2480
+- Validation Loss: 0.9039
 - Epoch: 0
 
 ## Model description
@@ -43,12 +43,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.1621     | 0.8490          | 0     |
+| 1.2480     | 0.9039          | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.32.0
+- Transformers 4.32.1
 - TensorFlow 2.13.0
 - Datasets 2.14.4
 - Tokenizers 0.12.1

config.json

@@ -1,51 +1,60 @@
 {
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
+  "classifier_dropout": 0.0,
   "d_ff": 3072,
   "d_kv": 64,
   "d_model": 768,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
+  "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "task_specific_params": {
     "summarization": {
-      "early_stopping": false,
-      "length_penalty": 1.0,
-      "max_length": 800,
-      "min_length": 50,
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
       "no_repeat_ngram_size": 3,
       "num_beams": 4,
       "prefix": "summarize: "
     },
     "translation_en_to_de": {
-      "early_stopping": false,
-      "max_length": 800,
+      "early_stopping": true,
+      "max_length": 300,
       "num_beams": 4,
       "prefix": "translate English to German: "
     },
     "translation_en_to_fr": {
-      "early_stopping": false,
-      "max_length": 800,
+      "early_stopping": true,
+      "max_length": 300,
       "num_beams": 4,
       "prefix": "translate English to French: "
     },
     "translation_en_to_ro": {
-      "early_stopping": false,
-      "max_length": 800,
+      "early_stopping": true,
+      "max_length": 300,
       "num_beams": 4,
       "prefix": "translate English to Romanian: "
     }
   },
+  "transformers_version": "4.32.1",
+  "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.27.0.dev0"
+  "transformers_version": "4.32.1"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5e6e98ff13b8af2aaefe070b943f29e055b3763cd0a63d72e94b0af8929471
+oid sha256:2b57fbdd2fa7f640fdc07abdcdc6424b823b1502042112add64b613e91eb0099
 size 1089544048